LTX-2.3-22b-IC-LoRA-LipDub
Released by Lightricks in 2026, LTX-2.3-22b-IC-LoRA-LipDub is a 22 billion parameter chat model. LTX-2.3-22b-IC-LoRA-LipDub is an open-weights chat model with roughly 22 billion parameters.
by Lightricks · 22B parameters
Best for
Ways to use LTX-2.3-22b-IC-LoRA-LipDub in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your Lightricks API key. osFoundry discovers LTX-2.3-22b-IC-LoRA-LipDub automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
LTX-2.3-22b-IC-LoRA-LipDub is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run LTX-2.3-22b-IC-LoRA-LipDub
LTX-2.3-22b-IC-LoRA-LipDub runs on a single 16GB consumer GPU (~14 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~53 GB).
LTX-2.3-22b-IC-LoRA-LipDub vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about LTX-2.3-22b-IC-LoRA-LipDub
Is LTX-2.3-22b-IC-LoRA-LipDub free to use?
LTX-2.3-22b-IC-LoRA-LipDub is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use LTX-2.3-22b-IC-LoRA-LipDub commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does LTX-2.3-22b-IC-LoRA-LipDub need?
Approximately 14 GB at Q4 quantisation, or 53 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run LTX-2.3-22b-IC-LoRA-LipDub locally?
Yes. LTX-2.3-22b-IC-LoRA-LipDub is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is LTX-2.3-22b-IC-LoRA-LipDub best at?
LTX-2.3-22b-IC-LoRA-LipDub is well-suited to any to any.
How do I use LTX-2.3-22b-IC-LoRA-LipDub in osFoundry?
Paste your Lightricks API key in the key dialog (or deploy the open weights for self-hostable models), assign LTX-2.3-22b-IC-LoRA-LipDub to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by Lightricks on May 11, 2026. Source: https://huggingface.co/Lightricks/LTX-2.3-22b-IC-LoRA-LipDub